Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4581 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3464. Min Act: -0.0000

Data Index: 489848 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3436. Min Act: -0.0000

Data Index: 98459 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3208. Min Act: -0.0000

Data Index: 965806 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3370. Min Act: -0.0000

Data Index: 240837 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1072279 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3203. Min Act: -0.0000

Data Index: 62760 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1126899 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3026. Min Act: -0.0000

Data Index: 13353 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1075224 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1275715 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3033. Min Act: -0.0000

Data Index: 319536 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1248067 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1300783 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2848. Min Act: -0.0000

Data Index: 330690 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.3103. Min Act: -0.0000

Data Index: 640511 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2819. Min Act: -0.0000

Data Index: 909700 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1164376 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2815. Min Act: -0.0000

Data Index: 920405 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2740. Min Act: -0.0000

Data Index: 643121 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2845. Min Act: -0.0000

Data Index: 370753 (C4 (Web Text))

Max Activating Token Index: 864